About
static quants of https://huggingface.co/NobodyExistsOnTheInternet/Llama-2-70b-x8-MoE-clown-truck
How did so many fit into that?
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-2-70b-x8-MoE-clown-truck-i1-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| PART 1 PART 2 PART 3 PART 4 | Q2_K | 170.8 | |
| PART 1 PART 2 PART 3 PART 4 | IQ3_XS | 190.5 | |
| P1 P2 P3 P4 P5 | IQ3_S | 202.0 | beats Q3_K* |
| P1 P2 P3 P4 P5 | Q3_K_S | 202.0 | |
| P1 P2 P3 P4 P5 | IQ3_M | 211.9 | |
| P1 P2 P3 P4 P5 | Q3_K_M | 223.1 | lower quality |
| P1 P2 P3 P4 P5 | Q3_K_L | 239.3 | |
| P1 P2 P3 P4 P5 P6 | IQ4_XS | 251.3 | |
| P1 P2 P3 P4 P5 P6 | Q4_K_S | 264.9 | fast, recommended |
| P1 P2 P3 P4 P5 P6 | Q4_K_M | 282.0 | fast, recommended |
| P1 P2 P3 P4 P5 P6 P7 | Q5_K_S | 319.7 | |
| P1 P2 P3 P4 P5 P6 P7 | Q5_K_M | 329.7 | |
| P1 P2 P3 P4 P5 P6 P7 P8 | Q6_K | 381.0 | very good quality |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 | Q8_0 | 492.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.